feat(qdrant): index content, is_active, and chunk_index on the chunks collection

Why:
- ADR-0002's keyword search needs a full-text index on content, which
  collection.py deliberately deferred to plan 002. is_active and chunk_index
  were unindexed while ingestion was the only reader; every /v1/points read path
  filters on them.

Changes:
- content gets a TEXT index with the multilingual tokenizer, which segments
  Persian correctly where the word tokenizer mishandles ZWNJ-joined compounds.
  No stemmer or stopword list: content is already letter-folded by
  normalize_persian_text at ingest, and the ranked Farsi lexical path is the
  benchmarked BM25 sparse vector, not this index.
- Tests assert content is TEXT rather than KEYWORD -- a keyword index would only
  match an entire chunk verbatim, which never happens and fails silently.
- Adds a test that a missing index is added to an already-live collection.

Impact:
- Requires re-running `python -m src.cli.qdrant_bootstrap`. Payload indexes are
  additive, so no collection rebuild and no re-embedding.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

tests/integration/qdrant/test_collection.py

@@ -65,10 +65,42 @@ async def test_ensure_chunks_collection_creates_the_payload_indexes(
         "order_id",
         "previous_chunk_id",
         "next_chunk_id",
+        "content",
+        "is_active",
+        "chunk_index",
     }
     # order_id must be numeric: Qdrant's Range/order_by reject keyword payloads.
     assert schema["order_id"].data_type == models.PayloadSchemaType.FLOAT
     assert schema["tenant_id"].data_type == models.PayloadSchemaType.KEYWORD
+    # `content` must be TEXT, not KEYWORD: ADR-0002's keyword search is a
+    # full-text match on it, and a keyword index would only match the entire
+    # chunk verbatim -- which never happens and would fail silently.
+    assert schema["content"].data_type == models.PayloadSchemaType.TEXT
+    assert schema["is_active"].data_type == models.PayloadSchemaType.BOOL
+    assert schema["chunk_index"].data_type == models.PayloadSchemaType.INTEGER
+
+
+async def test_ensure_chunks_collection_adds_a_missing_index_to_a_live_collection(
+    qdrant_client: AsyncQdrantClient, qdrant_settings: QdrantSettings
+) -> None:
+    """Payload indexes are additive, unlike vector config.
+
+    This is the operational claim the runbook makes when a new index ships:
+    re-running the bootstrap against an existing collection adds it in place, so
+    plan 002's `content`/`is_active`/`chunk_index` indexes do not require
+    recreating a collection that already holds a tenant's points.
+    """
+    await ensure_chunks_collection(qdrant_client, collection=qdrant_settings.collection)
+    await qdrant_client.delete_payload_index(
+        collection_name=qdrant_settings.collection, field_name="content"
+    )
+    info = await qdrant_client.get_collection(qdrant_settings.collection)
+    assert "content" not in info.payload_schema
+
+    assert not await ensure_chunks_collection(qdrant_client, collection=qdrant_settings.collection)
+
+    info = await qdrant_client.get_collection(qdrant_settings.collection)
+    assert info.payload_schema["content"].data_type == models.PayloadSchemaType.TEXT
 
 
 async def test_ensure_chunks_collection_is_idempotent(